68 citations · 114 across the 25 of their papers we have counts for
26 papers
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
Mingtian Tan, Palash Goyal, Mihir Parmar +6
Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical numerical observations insuffi…
Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization
Matthew Landers, Taylor W. Killian, Thomas Hartvigsen +1
Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form cohe…
Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
Lucas H. McCabe, Rimon Melamed, Thomas Hartvigsen +1
Many black-box techniques for quantifying the uncertainty of large language models (LLMs) rely on repeated LLM sampling, which can be computationally expensive. Therefore, practica…
SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces
Matthew Landers, Taylor W. Killian, Thomas Hartvigsen +1
The combinatorial structure of many real-world action spaces leads to exponential growth in the number of possible actions, limiting the effectiveness of conventional reinforcement…
Inferring Events from Time Series using Language Models
Mingtian Tan, Mike A. Merrill, Zack Gottesman +3
A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events a…
SkipSNN: Efficiently Classifying Spike Trains with Event-attention
Hang Yin, Yao Su, Liping Liu +3
Spike train classification has recently become an important topic in the machine learning community, where each spike train is a binary event sequence with \emph{temporal-sparsity…
BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
Matthew Landers, Taylor W. Killian, Hugo Barnes +2
Offline reinforcement learning in high-dimensional, discrete action spaces is challenging due to the exponential scaling of the joint action space with the number of sub-actions an…
Composable Interventions for Language Models
Arinbjorn Kolbeinsson, Kyle O'Brien, Tianjin Huang +8
Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of n…
Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks
Jack Gallifant, Shan Chen, Pedro Moreira +7
Medical knowledge is context-dependent and requires consistent reasoning across various natural language expressions of semantically equivalent phrases. This is particularly crucia…
PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
Devansh Jain, Priyanshu Kumar, Samuel Gehman +3
Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluatio…
TAXI: Evaluating Categorical Knowledge Editing for Language Models
Derek Powell, Walter Gerych, Thomas Hartvigsen
Humans rarely learn one fact in isolation. Instead, learning a new fact induces knowledge of other facts about the world. For example, in learning a korat is a type of cat, you als…
UniTS: A Unified Multi-Task Time Series Model
Shanghua Gao, Teddy Koker, Owen Queen +3
Although pre-trained transformers and reprogrammed text-based LLMs have shown strong performance on time series tasks, the best-performing architectures vary widely across tasks, w…
MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations
Bryan R Christ, Jonathan Kropko, Thomas Hartvigsen
Math word problems are critical K-8 educational tools, but writing them is time consuming and requires extensive expertise. To be educational, problems must be solvable, have accur…
Learning under Temporal Label Noise
Sujay Nagaraj, Walter Gerych, Sana Tonekaboni +3
Many time series classification tasks, where labels vary over time, are affected by label noise that also varies over time. Such noise can cause label quality to improve, worsen, o…
Machine Learning for Health symposium 2023 -- Findings track
Stefan Hegselmann, Antonio Parziale, Divya Shanmugam +5
A collection of the accepted Findings papers that were presented at the 3rd Machine Learning for Health symposium (ML4H 2023), which was held on December 10, 2023, in New Orleans,…
Multi-State Brain Network Discovery
Hang Yin, Yao Su, Xinyue Liu +3
Brain network discovery aims to find nodes and edges from the spatio-temporal signals obtained by neuroimaging data, such as fMRI scans of human brains. Existing methods tend to de…
Continuous Time Evidential Distributions for Irregular Time Series
Taylor W. Killian, Haoran Zhang, Thomas Hartvigsen +1
Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from. It is difficult to infer the value of a feature at an…
Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency
Owen Queen, Thomas Hartvigsen, Teddy Koker +3
Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to…
Interpretable Unified Language Checking
Tianhua Zhang, Hongyin Luo, Yung-Sung Chuang +7
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-…
Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks
Thomas Hartvigsen, Jidapa Thadajarassiri, Xiangnan Kong +1
Irregularly-sampled time series (ITS) are native to high-impact domains like healthcare, where measurements are collected over time at uneven intervals. However, for many classific…
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi +2
Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted…
Class-Specific Explainability for Deep Time Series Classifiers
Ramesh Doddaiah, Prathyush Parvatharaju, Elke Rundensteiner +1
Explainability helps users trust deep learning solutions for time series classification. However, existing explainability methods for multi-class time series classifiers focus on o…
Stop&Hop: Early Classification of Irregular Time Series
Thomas Hartvigsen, Walter Gerych, Jidapa Thadajarassiri +2
Early classification algorithms help users react faster to their machine learning model's predictions. Early warning systems in hospitals, for example, let clinicians improve their…
The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh +3
Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc exp…